© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99273
    Prev
    Next
    INDEX
    Explanations

    code structures

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric constants (especially floating‐point literals) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keduanya
    -1.52
     leksikon
    -1.45
    WEBP
    -1.38
     guantes
    -1.34
     begge
    -1.33
     Septembre
    -1.33
     kanton
    -1.33
     filtre
    -1.31
     Că
    -1.29
     vek
    -1.28
    POSITIVE LOGITS
     various
    1.49
     are
    1.38
     different
    1.30
     iniciativas
    1.30
     nossas
    1.29
    .
    1.28
     различных
    1.26
    </strong>
    1.26
     pomá
    1.26
    </b>
    1.24
    Activations Density 0.021%

    No Known Activations